On Learning Density Aware Embeddings
This work addresses noise tolerance in deep metric learning for applications like face and object recognition, representing an incremental improvement over existing methods.
The paper tackles the problem of noisy training data in deep metric learning by proposing Density Aware Metric Learning, which pulls embeddings towards dense cluster regions, resulting in faster convergence, reduced training time, and improved accuracy on cross-modal face and object recognition databases.
Deep metric learning algorithms have been utilized to learn discriminative and generalizable models which are effective for classifying unseen classes. In this paper, a novel noise tolerant deep metric learning algorithm is proposed. The proposed method, termed as Density Aware Metric Learning, enforces the model to learn embeddings that are pulled towards the most dense region of the clusters for each class. It is achieved by iteratively shifting the estimate of the center towards the dense region of the cluster thereby leading to faster convergence and higher generalizability. In addition to this, the approach is robust to noisy samples in the training data, often present as outliers. Detailed experiments and analysis on two challenging cross-modal face recognition databases and two popular object recognition databases exhibit the efficacy of the proposed approach. It has superior convergence, requires lesser training time, and yields better accuracies than several popular deep metric learning methods.